Leveraging sparse and shared feature activations for disentangled representation learning
This work addresses the challenge of applying disentangled representation learning to real-world data, which is significant for improving robustness in machine learning applications, though it builds incrementally on prior unsupervised and weakly-supervised methods.
The paper tackled the problem of learning disentangled representations from real-world data by leveraging knowledge from multiple supervised tasks, assuming each task depends on a subset of latent factors. It validated the approach on six real-world distribution shift benchmarks across images and text, showing successful transfer to practical settings.
Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with features activating sparsely across different tasks and information being shared as appropriate. Importantly, we never directly observe the factors of variations but establish that access to multiple tasks is sufficient for identifiability under sufficiency and minimality assumptions. We validate our approach on six real world distribution shift benchmarks, and different data modalities (images, text), demonstrating how disentangled representations can be transferred to real settings.